© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 51869
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¡Į
    -0.07
    ãģ°ãģĭãĤĬ
    -0.07
    å´Ńæĸ°çļĦ
    -0.07
    è¡ĮçļĦ
    -0.07
    jac
    -0.06
    ¢
    -0.06
    _ix
    -0.06
    (er
    -0.06
    ény
    -0.06
    beit
    -0.06
    POSITIVE LOGITS
    .getOwnProperty
    0.07
    ropol
    0.07
    åıĬ产åĵģ
    0.07
    izzi
    0.07
    åŀ£
    0.07
    nden
    0.07
    人èĥ½
    0.07
    åıĬ使çĶ¨
    0.06
    ëģĶ
    0.06
    åĴĮ使çĶ¨
    0.06
    Activations Density 0.021%

    No Known Activations